Skip to content

Rule Reference

SEC520lintai-ai-securitystablemarkdownwarn

AI markdown: `Read(*)` wildcard tool grant

AI-native markdown frontmatter grants `Read(*)` wildcard access

Provider
lintai-ai-security
Surface
markdown
Scope
per_file
Tier
stable
Severity
warn
Confidence
high
Detection
structural
Remediation
message_only

Activation Model

Preset Membership

This rule is part of the builtin activation graph through these preset memberships.

Lifecycle

Stable Lifecycle Contract

State

stable_gated

Graduation rationale

Checks AI-native frontmatter for exact `Read(*)` grants that expose unconstrained reading as shared default policy.

Deterministic signal basis

MarkdownSignals exact frontmatter token detection for `Read(*)` inside allowed-tools or allowed_tools.

Malicious corpus
skill-core-wildcard-allowed-tools
Benign corpus
skill-core-wildcard-allowed-tools-specific-safe
structured evidence required remediation reviewed
Canonical note

Structural stable rule intended as a high-precision check with deterministic evidence.

Nearby Signals

Related Rules

SEC520 / MD-READ-WILDCARD

SEC520 flags AI-native markdown frontmatter when allowed-tools or allowed_tools contains the exact wildcard token Read(*).

Why It Matters

Read(*) turns unrestricted file reading into shared default policy. In skills and instruction files, that is usually broader than the workflow actually needs and harder to defend in review.

Trigger Shape

  • AI-native markdown surface with parsed frontmatter
  • path is not fixture-like
  • allowed-tools or allowed_tools contains the exact token Read(*)

Safer Example

md
---
allowed-tools:
  - Read(./docs/**)
---